{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6835871934890747, "min": 0.6835871934890747, "max": 1.5101096630096436, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20507.615234375, "min": 20507.615234375, "max": 45810.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42109182476997375, "min": -0.09386252611875534, "max": 0.42109182476997375, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.01042175292969, "min": -22.620868682861328, "max": 113.05829620361328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04436005279421806, "min": -0.04436005279421806, "max": 0.13845233619213104, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.799774169921875, "min": -11.799774169921875, "max": 33.36701202392578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0692198753767159, "min": 0.06561577993228898, "max": 0.07310078314191491, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9690782552740226, "min": 0.4970424033804454, "max": 1.0482679011280804, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01305931257004323, "min": 0.0010743090805306879, "max": 0.014350588823227943, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18283037598060523, "min": 0.01504032712742963, "max": 0.2009082435251912, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.325197558300002e-06, "min": 7.325197558300002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010255276581620002, "min": 0.00010255276581620002, "max": 0.0036325135891621995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024417, "min": 0.1024417, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341838, "min": 1.3886848, "max": 2.6108378, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002539258300000001, "min": 0.0002539258300000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035549616200000016, "min": 0.0035549616200000016, "max": 0.12110269622, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008110116235911846, "min": 0.007772103417664766, "max": 0.35538655519485474, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1135416254401207, "min": 0.1088094487786293, "max": 2.487705945968628, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 469.7164179104478, "min": 443.3114754098361, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31471.0, "min": 15984.0, "max": 33945.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.351134309906568, "min": -1.0000000521540642, "max": 1.441906640926997, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.52599876374006, "min": -28.68740163743496, "max": 92.03159842640162, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.351134309906568, "min": -1.0000000521540642, "max": 1.441906640926997, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.52599876374006, "min": -28.68740163743496, "max": 92.03159842640162, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03921185414360683, "min": 0.03642199399068066, "max": 7.478350788354874, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6271942276216578, "min": 2.211957369298034, "max": 119.65361261367798, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688863542", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsPPO --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688865609" }, "total": 2066.9696694659997, "count": 1, "self": 0.4849854949998189, "children": { "run_training.setup": { "total": 0.04013743999996677, "count": 1, "self": 0.04013743999996677 }, "TrainerController.start_learning": { "total": 2066.444546531, "count": 1, "self": 1.2842613740281195, "children": { "TrainerController._reset_env": { "total": 4.310050741000055, "count": 1, "self": 4.310050741000055 }, "TrainerController.advance": { "total": 2060.759335786972, "count": 63572, "self": 1.355192248941421, "children": { "env_step": { "total": 1414.7336197490088, "count": 63572, "self": 1306.388631506964, "children": { "SubprocessEnvManager._take_step": { "total": 107.57190844203296, "count": 63572, "self": 4.6249945980733855, "children": { "TorchPolicy.evaluate": { "total": 102.94691384395958, "count": 62554, "self": 102.94691384395958 } } }, "workers": { "total": 0.7730798000118284, "count": 63572, "self": 0.0, "children": { "worker_root": { "total": 2061.8041078930282, "count": 63572, "is_parallel": true, "self": 866.7826200729878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005369365999968068, "count": 1, "is_parallel": true, "self": 0.003958430000011504, "children": { "_process_rank_one_or_two_observation": { "total": 0.001410935999956564, "count": 8, "is_parallel": true, "self": 0.001410935999956564 } } }, "UnityEnvironment.step": { "total": 0.054802997000024334, "count": 1, "is_parallel": true, "self": 0.0006365279999727136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005010070000253108, "count": 1, "is_parallel": true, "self": 0.0005010070000253108 }, "communicator.exchange": { "total": 0.05164130900004693, "count": 1, "is_parallel": true, "self": 0.05164130900004693 }, "steps_from_proto": { "total": 0.0020241529999793784, "count": 1, "is_parallel": true, "self": 0.00038433199961218634, "children": { "_process_rank_one_or_two_observation": { "total": 0.001639821000367192, "count": 8, "is_parallel": true, "self": 0.001639821000367192 } } } } } } }, "UnityEnvironment.step": { "total": 1195.0214878200404, "count": 63571, "is_parallel": true, "self": 33.13168551898798, "children": { "UnityEnvironment._generate_step_input": { "total": 22.24711207497876, "count": 63571, "is_parallel": true, "self": 22.24711207497876 }, "communicator.exchange": { "total": 1039.5491005280064, "count": 63571, "is_parallel": true, "self": 1039.5491005280064 }, "steps_from_proto": { "total": 100.09358969806715, "count": 63571, "is_parallel": true, "self": 19.473689728080558, "children": { "_process_rank_one_or_two_observation": { "total": 80.61989996998659, "count": 508568, "is_parallel": true, "self": 80.61989996998659 } } } } } } } } } } }, "trainer_advance": { "total": 644.6705237890214, "count": 63572, "self": 2.6793086309901355, "children": { "process_trajectory": { "total": 107.73312308703612, "count": 63572, "self": 107.52675375703643, "children": { "RLTrainer._checkpoint": { "total": 0.2063693299996885, "count": 2, "self": 0.2063693299996885 } } }, "_update_policy": { "total": 534.2580920709952, "count": 456, "self": 343.4085962739566, "children": { "TorchPPOOptimizer.update": { "total": 190.84949579703857, "count": 22809, "self": 190.84949579703857 } } } } } } }, "trainer_threads": { "total": 1.4060001376492437e-06, "count": 1, "self": 1.4060001376492437e-06 }, "TrainerController._save_models": { "total": 0.09089722299995628, "count": 1, "self": 0.0013472639998326486, "children": { "RLTrainer._checkpoint": { "total": 0.08954995900012364, "count": 1, "self": 0.08954995900012364 } } } } } } }